Basket-based Softmax

01/23/2022
by   Qiang Meng, et al.
0

Softmax-based losses have achieved state-of-the-art performances on various tasks such as face recognition and re-identification. However, these methods highly relied on clean datasets with global labels, which limits their usage in many real-world applications. An important reason is that merging and organizing datasets from various temporal and spatial scenarios is usually not realistic, as noisy labels can be introduced and exponential-increasing resources are required. To address this issue, we propose a novel mining-during-training strategy called Basket-based Softmax (BBS) as well as its parallel version to effectively train models on multiple datasets in an end-to-end fashion. Specifically, for each training sample, we simultaneously adopt similarity scores as the clue to mining negative classes from other datasets, and dynamically add them to assist the learning of discriminative features. Experimentally, we demonstrate the efficiency and superiority of the BBS on the tasks of face recognition and re-identification, with both simulated and real-world datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/02/2021

Face Recognition Using Sf_3CNN With Higher Feature Discrimination

With the advent of 2-dimensional Convolution Neural Networks (2D CNNs), ...
research
11/22/2021

GB-CosFace: Rethinking Softmax-based Face Recognition from the Perspective of Open Set Classification

State-of-the-art face recognition methods typically take the multi-class...
research
10/10/2022

BoundaryFace: A mining framework with noise label self-correction for Face Recognition

Face recognition has made tremendous progress in recent years due to the...
research
05/01/2019

AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations

The cosine-based softmax losses and their variants achieve great success...
research
08/24/2022

SubFace: Learning with Softmax Approximation for Face Recognition

The softmax-based loss functions and its variants (e.g., cosface, sphere...
research
06/11/2020

On Improving Temporal Consistency for Online Face Liveness Detection

In this paper, we focus on improving the online face liveness detection ...
research
08/20/2023

Towards Real-World Visual Tracking with Temporal Contexts

Visual tracking has made significant improvements in the past few decade...

Please sign up or login with your details

Forgot password? Click here to reset